Job Description:** Responsible for the development of recruitment recommendation algorithms for BOSS Zhipin’s Hong Kong operations, enhancing the recruitment/job-seeking experience for users. This includes, but is not limited to, aspects such as recall, coarse ranking, fine ranking, and matching strategy. **Job Responsibilities:** - Develop search and recommendation algorithms for BOSS Zhipin’s Hong Kong operations to enhance the recruitment/job-seeking experience for different user groups, covering aspects such as recall, coarse ranking, fine ranking, and matching strategy. - Fully understand the challenges and issues in the job recruitment scene, and transform user experience problems and business issues into algorithm model challenges. - Keep track of the latest algorithms and research trends in the industry and apply them to practical work, such as interest modeling, multi-objective, reinforcement learning, and the latest LLMs. **Job Requirements:** - Holds a Bachelor’s, Master’s, or PhD degree in Computer Science, Data Science, Artificial Intelligence, or a related field from a 985 & 211 university or a globally recognized university. - Holds a Hong Kong work visa or relevant qualifications. - Proficient in one or more programming languages such as Python and Java, and familiar with mainstream AI development environments like TensorFlow. - Experience in data mining, machine learning, deep learning, or NLP, and familiar with common models in the recommendation and search domains. - Knowledgeable about big data processing technologies and distributed computing frameworks, and familiar with the architecture of recommendation systems. - Strong learning ability and passionate about algorithmic work. - Curious and passionate about using algorithms to solve practical problems and continuously striving for optimized services. - Open-minded and rational, capable of communicating clearly and concisely with others. - Good English reading and writing skills, with adequate listening and speaking abilities. Familiarity with Cantonese is preferred.